PROJECT MANAGEMENT

AI weekly briefing on dependency bottlenecks across tools

Each week, an agent reads dependencies from Asana and GitHub, reasons about which tasks block the most downstream work.

CategoryProject Management
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule
  • ActionFetch dependencies from Asana and GitHubAsanaAsana
  • ActionPull linked PRs and issues from GitHubGitHubGitHub
  • LogicScore bottlenecks by downstream impact and draft briefingOpenAI
  • OutputPost bottleneck briefing to SlackSlack

What it does

An agent pulls task dependencies from Asana and linked engineering work from GitHub, then reasons across them to explain — in plain language — which items are the real bottlenecks: the ones blocking the most downstream work or sitting on the longest chains. It produces a narrative briefing, not just a list, including suggested owners and next actions.

When to use it

Use it for a Monday leadership or PM briefing when raw blocker lists are too noisy to act on. The agent prioritizes by downstream impact and writes the "so what," which a deterministic report can't.

How it works

  1. 1A weekly schedule starts the agent.
  2. 2The agent fetches tasks and dependencies from Asana and related PRs/issues from GitHub.
  3. 3It scores each item by downstream blocking impact and chain depth, and identifies likely deadlock risks.
  4. 4It drafts a prioritized briefing with reasoning and recommended owners.
  5. 5It posts the briefing to a Slack channel for the weekly review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AsanaTasks, projects, milestones — everywhere.
  2. 2
    Connect GitHubRepos, issues, pull requests, actions.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect OpenAIModels, embeddings, files.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.